TraDE: Network and Traffic-aware Adaptive Scheduling for Microservices Under Dynamics
🤖 AI Summary
To address performance degradation of microservices under dynamic network conditions and variable workloads, this paper proposes TraDE, an adaptive container rescheduling framework. TraDE jointly models the dual dynamics of runtime network latency and request traffic—novel in prior work—enabling fine-grained, low-overhead online rescheduling via real-time topology awareness, lightweight latency prediction, and reinforcement learning–driven decision-making. The framework is natively compatible with Kubernetes and supports continuous, self-adaptive optimization. Experimental evaluation demonstrates that TraDE outperforms NetMARKS by reducing average response time by 48.3%, increasing throughput by 1.4×, and achieving a goodput rate of 95.36%. These results significantly enhance system robustness and practical deployability in dynamic cloud environments.
Application Category
📝 Abstract
The transition from monolithic architecture to microservices has enhanced flexibility in application design and its scalable execution. This approach often involves using a computing cluster managed by a container orchestration platform, which supports the deployment of microservices. However, this shift introduces significant challenges, particularly in the efficient scheduling of containerized services. These challenges are compounded by unpredictable scenarios such as dynamic incoming workloads with various execution traffic and variable communication delays among cluster nodes. Existing works often overlook the real-time traffic impacts of dynamic requests on running microservices, as well as the varied communication delays across cluster nodes. Consequently, even optimally deployed microservices could suffer from significant performance degradation over time. To address these issues, we introduce a network and traffic-aware adaptive scheduling framework, TraDE. This framework can adaptively redeploy microservice containers to maintain desired performance amid changing traffic and network conditions within the hosting cluster. We have implemented TraDE as an extension to the Kubernetes platform. Additionally, we deployed realistic microservice applications in a real compute cluster and conducted extensive experiments to assess our framework's performance in various scenarios. The results demonstrate the effectiveness of TraDE in rescheduling running microservices to enhance end-to-end performance while maintaining a high goodput ratio. Compared with the existing method NetMARKS, TraDE outperforms it by reducing the average response time of the application by up to 48.3%, and improving the throughput by up to 1.4x while maintaining a goodput ratio of 95.36% and showing robust adaptive capability under sustained workloads.
Problem
Research questions and friction points this paper is trying to address.
Optimizing microservice scheduling under dynamic workloads and network delays
Addressing performance degradation from real-time traffic impacts on microservices
Adaptively redeploying services to maintain performance in changing cluster conditions
Innovation
Methods, ideas, or system contributions that make the work stand out.
Adaptive redeployment of microservices for performance
Network and traffic-aware scheduling in Kubernetes
Real-time rescheduling under dynamic workload conditions
🔎 Similar Papers
No similar papers found.
